Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "acting" or related entities in the context of events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.22
    3:0.04
    4:0.24
    5:0.06
    6:0.02
    7:0.02
    8:0.06
    9:0.15
    10:0.04
    11:0.02
    Negative Logits
    ologies
    -1.39
     Gleaming
    -1.28
    historic
    -1.23
    BuyableInstoreAndOnline
    -1.23
     millennium
    -1.20
    luaj
    -1.19
     flavors
    -1.18
     smile
    -1.18
    imar
    -1.17
     Dalai
    -1.15
    POSITIVE LOGITS
    xus
    1.56
    dq
    1.50
    iton
    1.41
    GGGG
    1.35
    bernatorial
    1.35
    五
    1.31
     rall
    1.30
    ittal
    1.30
    rity
    1.28
     dispatch
    1.28
    Act Density 0.009%

    No Known Activations